Skip to main content

visual speech

Showing 1 - 1 of 1 resources. Too many results? Use the search filters to refine your search.
Sort by
MULTISTREAM NEURAL ARCHITECTURES FOR CUED SPEECH RECOGNITION USING A PRE-TRAINED VISUAL FEATURE EXTRACTOR AND CONSTRAINED CTC DECODING
13 May 2022

MULTISTREAM NEURAL ARCHITECTURES FOR CUED SPEECH RECOGNITION USING A PRE-TRAINED VISUAL FEATURE EXTRACTOR AND CONSTRAINED CTC DECODING

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00